Ninth Edition Fifth Edition

Sixth Edition Third Edition

1
Introduction:
Sample, Population, Sampling,
Sampling With and Without
replacement. Sampling Distribution.
Standard Error
Quantitative Research, Types of
Quantitative Research.
Measurement Scales.

2
Introduction
Sampling provides an economical way to estimate the characteristics of a
large population. For a sample to be a random sample, every member of
the population must have an equal chance of being selected. When a
sample is chosen at random from a population, it is said to be an
unbiased sample. That is, the sample, for the most part, is representative
of the population. Conversely, if a sample is selected incorrectly, it may be
a biased sample. Samples are said to be biased samples when some type
of systematic error has been made in the selection of the subjects First,
we shall review some concepts related to sampling and then briefly
discuss a few of the basic sampling procedures.
Population and Sample
Statisticians gather data from a sample. They use this information to
make inferences about the population that the sample represents. Thus,
sample and population are relative terms. A population is a whole and a
sample is a fraction or segment of that whole. The process of selecting
the sample to draw conclusions about the population under study is called
sampling.

3
Parameter and Statistic
A numerical value calculated from the population is called parameter.
Parameters are usually denoted by Greek letters. A parameter is a
constant because it remains fixed throughout the sampling process.
Examples of parameter are: , 2, .
A numerical value calculated from the sample is called statistic. Statistics
are usually denoted by Roman letters. A statistic is a variable because it
changes from sample to sample. Examples of statistics are X , s2 or S2.
Sampling with Replacement and without Replacement
A sampling procedure in which sampled items are returned to the
population after being picked, so that some members of the population
can appear in the sample more than once is called sampling with
replacement. A sampling procedure in which sampled items are not
returned to the population after being picked, so that no member of the
population can appear in the sample more than once is called sampling
without replacement.
Purposes (Aims) of the Sampling
The two basic purposes of sampling are:
1. To obtain maximum information about the characteristics of the 4
population with minimum cost, time and effort.
2. To find the reliability of the estimates derived from the sample.
Advantages of Sampling
The following are the principal advantages of the sampling as compared
with complete enumeration. They are:
1. Sampling saves time and money.
2. Sampling provides measures of reliability.
3. Sampling is the only method to obtain information when population is
infinite.
4. More detailed information can be obtained from the sampling unit.
5. It saves labor, so trained personals can be employed in the available
resources.
6. It is more economic as it is cheaper to collect information from only a
part of population.
Sample Design
A definite plan for obtaining a sample from a given population is
called a sample design. A sample design is specified before any data are
collected. There are two types of sampling designs:
(i) Probability Sampling
(ii) Non-Probability Sampling
5
Probability and Non-Probability Sampling
Probability sampling is a procedure in which the sample is selected
in such a way that every element of a population has a known or non-zero
(not necessarily equal) probability of its being included in the sample. A
probability sampling is also called random sampling. The major types of
probability sampling are simple random sampling, stratified random
sampling, systematic sampling, cluster sampling, etc. The advantage of
probability sampling is that it provides a valid estimate of sampling error.
Non-probability sampling is a procedure in which we cannot assign
to an element of the population the probability of its being included in the
sample. The disadvantage of non-probability sampling is that the reliability
of the sample results cannot be determined in terms of probability. Non-
probability sampling techniques are, purposive sampling, Quota sampling
etc.
Sampling Distribution
The probability distribution of the values of a statistic such as
mean, a proportion etc., is called a sampling distribution.
For example, the distribution of the sample mean is a sampling
distribution of the mean, and the distribution of the sample proportion is a
sampling distribution of the proportion. 6
Standard Error (S.E)
The standard deviation of a sampling distribution of a sample
statistic is called the standard error of the statistic. It is abbreviated as S.E
Properties of Sampling Distribution of Mean ( X )
The sampling distribution of has the following properties.
1.  x =  (whether sampling is done with replacement or without replacement)
X
where  x =  x f( x ) and  = N
2 
2. x = and x =  n = S.E
n 2 2
  X   X 
2  = −  
where  x = ∑ x 2f( x ) – [∑ x f( x )]2 and N  N 
In case of sampling without replacement, the above relation can be written
as   N −n
 N −n
2  
x = n  N − 1  
and S.E = x =
n N −1

7
Example # 1 A population consists of values 2, 4, 6 and 8.
Take all possible samples of size 2 which can be drawn with
replacement. Find means of these samples and form the
sampling distribution of the sample means. Also verify that:
2 
(i)  x =  (ii) x = n
Solution
Here N = 4, n = 2 Population = 2, 4, 6, 8. Sampling WR
Possible samples are (N)n = (4)2 = 16
Samples Samples Samples Samples
x Mean x x Mean x
2, 2 2 6, 2 4
2, 4 3 6, 4 5
2, 6 4 6, 6 6
2, 8 5 6, 8 7
4, 2 3 8, 2 5
4, 4 4 8, 4 6
4, 6 5 8, 6 7
4, 8 6 8, 8 8
8
Frequency Distribution Sampling Mean and Variance of
of x Distribution of x sampling distribution
x Tally f x f( x ) x f( x ) x 2 f( x )
2 | 1 2 1/16 2/16 4/16
3 || 2 3 2/16 6/16 18/16
4 ||| 3 4 3/16 12/16 48/16
5 |||| 4 5 4/16 20/16 100/16
6 ||| 3 6 3/16 18/16 108/16
7 || 2 7 2/16 14/16 98/16
8 | 1 8 1/16 8/16 64/16
∑ – 16 – 1 80/16 440/16
80
 x =  x f( x ) = =5 (i)
16
 x x
2 = ∑ 2f( x ) – [∑ f( )]2 = 440 − (5)2 = 2.5
x (ii)
x 16
Mean and variance of the population
X 2 4 6 8 X = 20
X2 4 16 36 64 120 = X2
9
 X 20
 = N
= = 5 (iii)
4
2
X 2 120 2
 =
 X
−   = − ( 5) = 5
N  N  4
 5
= = 2.5 (iv)
n 2
From equation number (i) and (iii)
x =  verified
From equation number (ii) and (iv)
2 
x =
n
verified

10
Example # 2 A population consists of values 3, 6 and 9. Take
all possible samples of size 3 with replacement. Form the
sampling distribution of samples mean X
Hence state and verify the relation between
(i) The mean of X and the population mean.
(ii) The variance of X and population variance.
(iii) The standard error of X and the population
standard deviation.
Samples Samples Samples Samples means
Solution Here n = 3, N = 3, x means x x x
3, 3, 3 3 6, 6, 9 7
Population = 3, 6, 9. 3, 3, 6 4 6, 9, 3 6
Sampling WR 3, 3, 9 5 6, 9, 6 7
3, 6, 3 4 6, 9, 9 8
Possible samples are 3, 6, 6 5 9, 3, 3 5
3, 6, 9 6 9, 3, 6 6
(N)n = (3)3 = 27 3, 9, 3 5 9, 3, 9 7
3, 9, 6 6 9, 6, 3 6
3, 9, 9 7 9, 6, 6 7
6, 3, 3 4 9, 6, 9 8
6, 3, 6 5 9, 9, 3 7
6, 3, 9 6 9, 9, 6 8
6, 6, 3 5 9, 9, 9 9
6, 6, 6 6 11
Sampling distribution of sample mean X
x Tally f f( )
x x f( x) x 2 f(
x)
3 | 1 1/27 3/27 9/27

4 |||| 3 3/27 12/27 48/27

5 6 6/27 30/27 150/27

6 7 7/27 42/27 252/27

7 6 6/27 42/27 294/27

8 ||| 3 3/27 24/27 192/27

9 | 1 1/27 9/27 81/27

∑ – 27 1 162/27 1026/27

162
 x =  x f( x ) = =6 (1)
27 1026 2
x2 = ∑ x 2f( x) – [∑ x f( x )]2 = − (6) = 2 (2)
27
Mean and variance of the population
X 3 6 9 X = 18
X2 9 36 81 X2 = 126
x = = 1.414 ...(3) 12
  X 18
 = N = 3 = 6 …(4)
2 2
  X   X  126 2
 = −   = − ( 6) = 6
N  N  3
 = 6 = 2.4495
 6
= =2 ...(5)
n 3

n = 2.4495 / 1.732 = 1.414 …(6)

We have to verify that

(i) From equation number (1) and (4) x=
6=6 verified.
 
(ii) From equation (2) and (5) x2 =
n
2 = 2 verified.
(iii) From equation number (3) and (6)  x =

n 13
1.414 = 1.414 verified.
Example # 3 A population consists of values 3, 6, 9, 12, 15.
Draw all possible samples of size 2 without replacement. Form
the sampling distribution of sample means and verify the
results:
2   N − n 
(i)  x =  (ii) x = n  N − 1 
 
Solution

Here n = 2, N = 5 population = 3, 6, 9, 12, 15. Sampling WOR

Possible samples which can be drawn without replacement = NCn = 5C2 = 10

Samples Samples Samples Samples

x mean x x mean x
3, 6 4.5 6, 12 9
3, 9 6 6, 15 10.5
3, 12 7.5 9, 12 10.5
3, 15 9 9, 15 12
6, 9 7.5 12, 15 13.5

14
Sampling distribution of sample mean X
x f f( x ) x f( x ) x 2 f( x )
4.5 1 1/10 4.5/10 20.25/10
6 1 1/10 6/10 36/10
7.5 2 2/10 15/10 112.5/10
9 2 2/10 18/10 162/10
10.5 2 2/10 21/10 220.5/10
12 1 1/10 12/10 144/10
13.5 1 1/10 13.5/10 182.25/10
Total 10 1 90/10 877.5/10

90
 x =  x f( x ) = =9 (i)
10 877.5 2
2 2 2
x = ∑ x f( x ) – [∑x f( x )] = 10 − (9) = 6.75 (ii)

Mean and variance of the population X X2

3 9
6 36
9 81
12 144
15 225 15
X = 45 X2 = 495
 X 45
 = N
= = 9 (iii)
5
2

 =
X X
− 
 2= 495 − 9 2 = 18
 ( )
N 5
 N 
   N − n    5 − 2 
 =   = 6.75 (iv)
n  N −1  2  5 −1 
From equation number (i) and (iii)
x = 
From equation number (ii) and (iv)
2   N −n

x =  
n  N −1 

16
Example # 4 A population consists of values 6, 6, 9, 15, 18.
Draw all possible samples of size 3 without replacement. Form
the sampling distribution of sample means and verify the
results:
2   N − n 
(i)  x =  (ii) x = n  N − 1 
 
Solution

Here n = 3, N = 5 Population = 6, 6, 9,15,18. Sampling WOR

Possible samples which can be drawn without replacement = NCn = 5C3 = 10
Samples Samples Samples Samples
x mean x x mean x
6, 6, 9 7 6, 15, 18 13
6, 6, 15 9 6, 9, 15 10
6, 6, 18 10 6, 9, 18 11
6, 9, 15 10 6, 15, 18 13
6, 9, 18 11 9, 15, 18 14

17
Sampling distribution of sample mean X
x f f( x) x f( x ) x 2 f( x )
7 1 1/10 7/10 49/10
9 1 1/10 9/10 81/10
10 3 3/10 30/10 300/10
11 2 2/10 22/10 242/10
13 2 2/10 26/10 338/10
14 1 1/10 14/10 196/10
Total 10 1 108/10 1206/10
(i)  x =  x f( x ) = 108/10 = 10.8 ...(1)
(ii)  x2 = ∑ x 2f( x) – [∑ x f( x)]2 = 1206/10 – (10.8)2 = 3.96 …(2)
Mean and variance of the population
X X2
6 36
6 36
9 81
15 225
18 324
X = 54 X2 = 702
18
 X 54
 =  = = 10.8 …(3)
N 5
2 2
X X 2 702
 = −   = − (10.8 ) = 23.76
N  N  5
   N − n    5 − 3 
 =   = 3.96 ...(4)
n  N −1  3  5 −1 

From equation number (1) and (3)

x = 
10.8 = 10.8 verified.

From equation number (2) and (4)

  N − n 
x2 =  
n  N −1 
3.96 = 3.96 verified.

19